+0
日增长
996
stars
62
forks
18
watchers
17
prs
40
issues
0
releases
README
Parakeet MLX
An implementation of the Parakeet models - Nvidia's ASR(Automatic Speech Recognition) models - for Apple Silicon using MLX.
Installation
[!NOTE]
Make sure you have ffmpeg installed on your system first, otherwise CLI won't work properly.
Using uv - recommended way:
bash
uv add parakeet-mlx -U
Or, for the CLI:
bash
uv tool install parakeet-mlx -U
Using pip:
bash
pip install parakeet-mlx -U
CLI Quick Start
bash
parakeet-mlx [OPTIONS]
Arguments
- audio_files: One or more audio files to transcribe (WAV, MP3, etc.)
Options
- --model (default: mlx-community/parakeet-tdt-0.6b-v3, env: PARAKEET_MODEL)
- Hugging Face repository of the model to use
- https://huggingface.co/collections/mlx-community/parakeet
- --output-dir (default: current directory)
- Directory to save transcription outputs
- --output-format (default: srt, env: PARAKEET_OUTPUT_FORMAT)
- Output format (txt/srt/vtt/json/all)
- --output-template (default: {filename}, env: PARAKEET_OUTPUT_TEMPLATE)
- Template for output filenames, {parent}, {filename}, {index}, {date} is supported.
- --highlight-words (default: False)
- Enable word-level timestamps in SRT/VTT outputs
- --verbose / -v (default: False)
- Print detailed progress information
- --decoding (default: greedy, env: PARAKEET_DECODING)
- Decoding method to use (greedy or beam)
- beam is only available at TDT/RNNT models for now
- --chunk-duration (default: 120 seconds, env: PARAKEET_CHUNK_DURATION)
- Chunking duration in seconds for long audio, 0 to disable chunking
- --overlap-duration (default: 15 seconds, env: PARAKEET_OVERLAP_DURATION)
- Overlap duration in seconds if using chunking
- --beam-size (default: 5, env: PARAKEET_BEAM_SIZE)
- Beam size (only used while beam decoding)
- --length-penalty (default: 0.013, env: PARAKEET_LENGTH_PENALTY)
- Length penalty in beam. 0.0 to disable (only used while beam decoding)
- --patience (default: 3.5, env: PARAKEET_PATIENCE)
- Patience in beam. 1.0 to disable (only used while beam decoding)
- --duration-reward (default: 0.67, env: PARAKEET_DURATION_REWARD)
- From 0.0 to 1.0, 0.5 to favor duration logprobs more. (only used while beam decoding in TDT models)
- --max-words (default: None, env: PARAKEET_MAX_WORDS)
- Max words per sentence
- --silence-gap (default: None, env: PARAKEET_SILENCE_GAP)
- Split sentence if it exceeds silence gap provided (seconds)
- --max-duration (default: None, env: PARAKEET_MAX_DURATION)
- Max sentence duration (seconds)
- --fp32 / --bf16 (default: bf16, env: PARAKEET_FP32 - boolean)
- Determine the precision to use
- --full-attention / --local-attention (default: full-attention, env: PARAKEET_LOCAL_ATTENTION - boolean)
- Use full attention or local attention (Local attention reduces intermediate memory usage)
- Expected usage case is for long audio transcribing without chunking
- --local-attention-context-size (default: 256, env: PARAKEET_LOCAL_ATTENTION_CTX)
- LocalTop issues
#37Feature: Consistent cache_dir to prevent duplicate downloads7 comments · 2025-09-16#16Devices running macOS 14 are unable to run parakeet-mlx7 comments · 2025-05-17#20Push-to-talk to output transcript anywhere3 comments · 2025-05-26#11I've just finished a GUI, and the kernel utilizes parakeet-mlx.3 comments · 2025-05-10#24Insights on porting parakeet-mlx real time transcription on rpi 5 or other embedded devices2 comments · 2025-06-20#46Potential hallucination and performance issues in Parakeet MLX - Request for community feedback1 comments · 2025-12-30#44Support text prompts1 comments · 2025-10-29
Discussions
#60LiveLingo: live lecture subtitles and notes on macOS, transcribed with parakeet-mlx0 comments · 2026-10-01#26Multilingual version1 comments · 2025-07-02#21Swift version of parakeet-mlx2 comments · 2025-05-28#17A Free macOS App Built on parakeet-mlx – Looking for Feedback3 comments · 2025-05-17#15Parakeet MLX 0.2.7 Benchmark Result5 comments · 2025-05-16